Study on a Poisson's equation solver based on deep learning technique

In this work, we investigated the feasibility of applying deep learning techniques to solve 2D Poisson's equation. A deep convolutional neural network is set up to predict the distribution of electric potential in 2D. With training data generated from a finite difference solver, the strong approximation capability of the deep convolutional neural network allows it to make correct prediction given information of the source and distribution of permittivity. Numerical experiments show that the predication error can reach below one percent, with a significant reduction in CPU time compared with the traditional solver based on finite difference methods.

[1]  He Ming Yao,et al.  Machine learning based MoM (ML-MoM) for parasitic capacitance extractions , 2016, 2016 IEEE Electrical Design of Advanced Packaging and Systems (EDAPS).

[2]  H. V. D. Vorst,et al.  Model Order Reduction: Theory, Research Aspects and Applications , 2008 .

[3]  Shenheng Xu,et al.  Quasi-Periodic Array Modeling Using Reduced Basis Method , 2017 .

[4]  Qi-Jun Zhang,et al.  Artificial neural networks for RF and microwave design - from theory to practice , 2003 .

[5]  Allen Taflove,et al.  Computational Electrodynamics the Finite-Difference Time-Domain Method , 1995 .

[6]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[7]  Ah Chung Tsoi,et al.  Face recognition: a convolutional neural-network approach , 1997, IEEE Trans. Neural Networks.

[8]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[9]  Roger F. Harrington,et al.  Field computation by moment methods , 1968 .

[10]  W. Marsden.  I and J , 2012 .

[11]  A. Ng.  Feature selection, L1 vs. L2 regularization, and rotational invariance , 2004, Twenty-first international conference on Machine learning - ICML '04.

[12]  Kyle Mills,et al.  Deep learning and the Schrödinger equation , 2017, ArXiv.

[13]  Michel Nakhla,et al.  A neural network modeling approach to circuit optimization and statistical design , 1995 .

[14]  Fan Yang,et al.  Quasi-Periodic Array Modeling Using Reduced Basis Method , 2017, IEEE Antennas and Wireless Propagation Letters.

[15]  김덕영.  [신간안내] Computational Electrodynamics (the finite difference time - domain method) , 2001 .

[16]  Ahmed K. Noor,et al.  Reduced Basis Technique for Nonlinear Analysis of Structures , 1979 .

[17]  Niloy J. Mitra,et al.  Learning A Physical Long-term Predictor , 2017, ArXiv.

[18]  Wei Li,et al.  Convolutional Neural Networks for Steady Flow Approximation , 2016, KDD.

[19]  Gene H. Golub,et al.  Matrix computations (3rd ed.) , 1996 .

[20]  Rob Fergus,et al.  Learning Physical Intuition of Block Towers by Example , 2016, ICML.

[21]  Carla E. Brodley,et al.  Proceedings of the twenty-first international conference on Machine learning , 2004, International Conference on Machine Learning.

[22]  Ken Perlin,et al.  Accelerating Eulerian Fluid Simulation With Convolutional Networks , 2016, ICML.

[23]  Qi-Jun Zhang,et al.  Neural Networks for RF and Microwave Design , 2000 .

[24]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[25]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[26]  Robert H. Halstead,et al.  Matrix Computations , 2011, Encyclopedia of Parallel Computing.

[27]  Dieter Fox,et al.  SE3-nets: Learning rigid body motion using deep neural networks , 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[28]  Carretera de Valencia,et al.  The finite element method in electromagnetics , 2000 .

[29]  R. Mittra,et al.  Characteristic basis function method: A new technique for efficient solution of method of moments matrix equations , 2003 .

[30]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.